@Image 1 is the performer — preserve her exact identity: face, hair, and all defining features. Wardrobe for this concept: oversized black leather jacket, gold rope chain, baggy raw denim, clean white tee. (Audio1) is the finished master track — dusty 90s boom-bap, cracking drum break, upright bass loop. The only audio; no invented music, no new vocals. SHE RAPS THE VOCAL ON CAMERA — PRECISE LIPSYNC IS THE TOP PRIORITY. Mouth articulates every syllable of (Audio1) exactly on time; face visible and sharp through every vocal line, no cutaways mid-word. LIPSYNC MAP: 0.0–0.5 instrumental. 0.5–2.8 [opening lines] + [ad-lib]. 3.2–6.7 [verse]. 7.5–13.7 [hook, repeated verbatim, escalated]. 14.5–15.0 instrumental hold. Music-video route: golden-era cypher. Director thesis: Brooklyn rooftop at golden hour — she raps at the lens while five dancers in matching 90s streetwear form a cypher circle around her that tightens one step on every bar; by the final hook they stand shoulder-to-shoulder, heads nodding in exact unison. Visual world: tar-paper rooftop, water towers and skyline haze behind, low warm sun as the single key, long shadows. 5 female dancers in earth-tone 90s baggy fits, Timberland palette; her gold chain catches the sun and keeps her instantly readable. Palette: amber, brick, denim blue. No neon, no lens flares. Shot flow: 0–2.8s wide push-in through the loose circle to her at center rapping the opening. 2.8–3.2s on the ad-lib all five snap one step inward. 3.2–6.7s medium: she rides the verse with subtle bounce, circle stepping in per bar; camera slow orbit keeping her mouth front. 7.5–10s chest-up close, hook doubled in intensity, nodding heads soft-focus behind. 10–13.7s circle fully closed around her, camera cranes slightly up, she raps skyward. 13.7–15s final beat: all six freeze mid-nod, sun flare held. Loopable. Performance rules: laid-back but surgical diction, jaw loose, eyes locked to lens; dancers never mouth the words — only she raps. Continuity: same six women, same wardrobe, same rooftop, same sun position. Audio intent: (Audio1) only; faint city air, distant traffic. Quality bar: expensive 90s hip-hop documentary aesthetic, 16mm grain feel, no AI gloss, no glow.